server
server copied to clipboard
Enhance OTEL testing to capture and verify Cancellation Requests and Non-Decoupled model inference.
Added tests for
- For request cancellations, make sure spans are ended properly in various scenarios
- Verify tracing behavior, after this PR: https://github.com/triton-inference-server/server/pull/6017
Tests added
- test_non_decoupled() : Verify tracing for a non-decoupled inference
- test_grpc_trace_all_input_required_model_cancel() : Verify trace after an inference request is cancelled in COMPUTE Phase
- test_grpc_trace_model_cancel_in_queue() : Verify trace after an inference request is cancelled in QUEUE before COMPUTE Phase
Could you please add a description, clarifying what tests were added?
Could you please attach a picture of a trace as displayed in jaeger with cancelled request.
Another question, have you considered cases when request was cancelled, when it was in a queue and when it was already in a compute stage?
Could you please attach a picture of a trace as displayed in jaeger with cancelled request.
Another question, have you considered cases when request was cancelled, when it was in a queue and when it was already in a compute stage?
Could you please attach a picture of a trace as displayed in jaeger with cancelled request.
Another question, have you considered cases when request was cancelled, when it was in a queue and when it was already in a compute stage?
Fixed this, added a model which waits for a delay before executing hence cancellation request is recieved before the execution starts
Can you update the PR title to be more descriptive? (cancellation, decoupled responses, etc. rather than JIRA ticket number)
I think it's in a good state. Let's address Ryan's comment and provide a clear description for 3 tests, added in this PR, to the PR description